Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    at [institution]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paddock
    0.31
     backstory
    0.30
     exothermic
    0.30
     biodegrad
    0.29
     charred
    0.29
     villain
    0.29
     flammable
    0.29
     맛있
    0.29
     sanding
    0.29
     건물
    0.29
    POSITIVE LOGITS
     universities
    0.39
     Institute
    0.39
     Chicago
    0.38
     Universidade
    0.37
     National
    0.36
     London
    0.36
     Instituto
    0.36
     Munich
    0.36
    Institute
    0.36
     Istituto
    0.36
    Act Density 0.049%

    No Known Activations